Supporting Reasoning with Deep Semantic AI for European Calls in Brussels
"Gianluca Sensidoni presents innovative AI/NLU algorithms to enhance understanding and generate insights from language using a hybrid NLU approach. The proposed features aim to combat corruption and illicit drug activities effectively, leveraging semantic reasoning, emotions analysis, and stylometric insights. Explore the use of emotions and stylometric analysis for extracting human attributes in the field of deep semantic AI. Join SMI2G 2022 in Brussels to witness live demos and seek partnerships for creating impactful consortia. Discover a cutting-edge approach to knowledge graph creation and reasoning for actionable insights and information superiority."
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Supporting Reasoning by Deep Semantic AI/NLU algorithms SMI2G 2022, 16-17 May 2022, Brussels Gianluca Sensidoni - gsensidoni@expert.ai (Expert.ai SpA) Role: AI/NLU Semantic Algorithms provider European Calls: CL3-2022-FCT-01-05, CL3-2022-FCT-01-06, but also other EU calls at Cluster 3 Proposal activity: the ability to understand language and transform it into insights: A Knowledge Graph as core - a representation of the real world by concepts and semantic relationships + Machine/Deep learning on top (Hybrid NLU) The Disambiguation it distinguishes the correct meaning of words and expressions in context (NO Black Box) The Reasoning process - Hybrid NLU can mimic human reasoning while analysing unstructured contents so to produce Actionable Insight 1 Gianluca Sensidoni gsensidoni@expert.ai
Proposed NLU features CL3-2022-FCT-01-05 - Effective fight against corruption : Entities, Relations and Categories extractions to improve Intelligence picture; Reasoning by Semantic Patterns and Temporal References to infer modus operandi; Clustering of similar news so to unveil corruptive practices; Emotions analysis to understand social and economic impact; Analysing historical use cases to mitigate future similar events (EX-POST analysis). CL3-2022-FCT-01-06 - Effective fight against illicit drugs production and trafficking : Entities, Relations and Categories extractions to improve Intelligence picture; Emotions analysis to prevent buying/selling actions; Semantic unknown concepts extractions to discover new trends; Stylometric analysis to correlate Virtual IDs from Surface to Dark Nets; Precursors substances discovering used for drugs production. SMI2G 2022, 16-17 May 2022, Brussels A validated semantic deduction becomes part of the Knowledge Graph The same process can start again with a new and wider know-how. More know-how means more efficient prevention (EX-ANTE analysis) Information Superiority for Augmented DSS, Simulation & Prediction platform. 2 Gianluca Sensidoni gsensidoni@expert.ai
Why Emotions & Stylometric Analysis Extracting human factor attributes like the sequences structure of DNA SMI2G 2022, 16-17 May 2022, Brussels Highly distinctive trait for Cristoforetti 3 Gianluca Sensidoni gsensidoni@expert.ai
Conclusions Live FREE Demos at: https://try.expert.ai/ https://intelligenceapi.com/ SMI2G 2022, 16-17 May 2022, Brussels Looking for Core Partners creating Consortia: Coordinator System Integrator with Investigative platform DarkNets documents acquisition Expertise on lawful court-proof collection of crime evidence Domain experts and practitioners Expertise on Training LEAs 4 Gianluca Sensidoni gsensidoni@expert.ai
